pith. sign in

Audio augmen- tation for speech recognition,

2 Pith papers cite this work. Polarity classification is still indexing.

2 Pith papers citing it

fields

cs.CL 2

years

2019 2

verdicts

UNVERDICTED 2

representative citing papers

Essence Knowledge Distillation for Speech Recognition

cs.CL · 2019-06-26 · unverdicted · novelty 5.0

A single student model trained on essence knowledge from a teacher ensemble plus hard labels outperforms both a standard single model and the teacher ensemble itself on the Switchboard dataset.

citing papers explorer

Showing 2 of 2 citing papers.

  • Transfer Learning from Audio-Visual Grounding to Speech Recognition cs.CL · 2019-07-09 · unverdicted · none · ref 11

    Features from audio-visual semantic grounding models improve speech recognition when used as input, with earlier layers retaining more phonetic detail and deeper layers showing greater domain invariance.

  • Essence Knowledge Distillation for Speech Recognition cs.CL · 2019-06-26 · unverdicted · none · ref 11

    A single student model trained on essence knowledge from a teacher ensemble plus hard labels outperforms both a standard single model and the teacher ensemble itself on the Switchboard dataset.